{"ID":2850056,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.22691","arxiv_id":"2510.22691","title":"SALSA: Single-pass Autoregressive LLM Structured Classification","abstract":"Despite their impressive generalization capabilities, instruction-tuned Large Language Models often underperform on text classification benchmarks. We introduce SALSA, a coherent pipeline that combines structured prompting, class-to-token mapping, and parameter-efficient fine-tuning, thereby avoiding cold-start training. Each class label is mapped to a distinct output token, and prompts are constructed to elicit a single-token response. During inference, the model's output is projected only onto the logits of the relevant class tokens, enabling efficient and accurate classification in a single forward pass. SALSA achieves state-of-the-art results across diverse benchmarks, demonstrating its robustness and scalability for LLM-based classification applications.","short_abstract":"Despite their impressive generalization capabilities, instruction-tuned Large Language Models often underperform on text classification benchmarks. We introduce SALSA, a coherent pipeline that combines structured prompting, class-to-token mapping, and parameter-efficient fine-tuning, thereby avoiding cold-start trainin...","url_abs":"https://arxiv.org/abs/2510.22691","url_pdf":"https://arxiv.org/pdf/2510.22691v1","authors":"[\"Ruslan Berdichevsky\",\"Shai Nahum-Gefen\",\"Elad Ben Zaken\"]","published":"2025-10-26T14:28:42Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}